CN110362116A - Based on the transformer minitype bionic fish global path planning method for improving ant group algorithm - Google Patents
Based on the transformer minitype bionic fish global path planning method for improving ant group algorithm Download PDFInfo
- Publication number
- CN110362116A CN110362116A CN201910723996.1A CN201910723996A CN110362116A CN 110362116 A CN110362116 A CN 110362116A CN 201910723996 A CN201910723996 A CN 201910723996A CN 110362116 A CN110362116 A CN 110362116A
- Authority
- CN
- China
- Prior art keywords
- transformer
- grid
- bionic fish
- minitype bionic
- ant
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
- G05D1/0088—Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot characterized by the autonomous decision making process, e.g. artificial intelligence, predefined behaviours
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
- G05D1/10—Simultaneous control of position or course in three dimensions
Abstract
The present invention relates to a kind of based on the transformer minitype bionic fish global path planning method for improving ant group algorithm, its technical characterstic is: the following steps are included: step 1, establishing inside transformer surrounding three-dimensional grating map, transformer three-dimensional environment cartographic information being initialized；The differential seat angle of the potential field resultant force of grid shared by minitype bionic fish in step 2, calculating transformer Raster Data Model and the direction of motion of transformer minitype bionic fish and potential field resultant force；The probability selection moving direction of step 3, calculating transformer minitype bionic fish next step grid；Step 4 judges whether the current grid falls into trap, and taboo list is added in the current grid if not, ant is otherwise reentered into starting point and is restarted；Whether the mobile current location of step 5, interpretation transformer micro robot fish reaches target position described in step 1.The present invention scans for transformer minitype bionic fish no longer blindly, improves algorithm search speed and global optimizing ability.
Description
Technical field
The invention belongs to robot motion's trajectory planning techniques fields, are related to minitype bionic fish paths planning method, especially
It is a kind of based on the transformer minitype bionic fish global path planning method for improving ant group algorithm.
Background technique
Transformer minitype bionic fish needs to be maked an inspection tour in high-power transformer oil, and high-power transformer bulky is bionical
Fish moves about longer away from discrete time inside it, it is desirable that transformer Biomimetic Fish is swum under the premise of consumption less energy as far as possible
It moves to target point and therefore how to plan a shorter collisionless path in transformer, it is complete to the task of minitype bionic fish
At having great importance.Currently, robot motion's trajectory planning strategy is mostly based on two-dimensional space, although part two both at home and abroad
Dimension planning strategy can be applied to three-dimensional space, but for the trajectory planning of three-dimensional space, exists and occupies that memory space is big, it is multiple to calculate
Two-dimentional trajectory planning strategy is simply directly extended to three-dimensional space and infeasible by the distinctive problem of polygamy etc..Therefore,
How to formulate that a kind of memory space is small, calculates the motion trail planning method of simple three-dimensional space and be those skilled in the art urgently
The technical problem to be solved.
Summary of the invention
It is an object of the invention to overcome the deficiencies in the prior art, propose that a kind of design is reasonable, memory space is small, calculating is simple
Single transformer minitype bionic fish global path planning method based on improvement ant group algorithm.
The present invention solves its realistic problem and adopts the following technical solutions to achieve:
A kind of transformer minitype bionic fish global path planning method based on improvement ant group algorithm, comprising the following steps:
Step 1 establishes inside transformer surrounding three-dimensional grating map, transformer three-dimensional environment cartographic information is carried out initial
Change, the initialization and improvement ant colony of initial position and target position, Artificial Potential Field Method including transformer minitype bionic fish movement
The initialization of algorithm；
Step 2 is closed using the potential field of grid shared by the minitype bionic fish in Artificial Potential Field Method calculating transformer Raster Data Model
Power, and the differential seat angle of the direction of motion of calculating transformer minitype bionic fish and potential field resultant force；
Step 3, using improve ant group algorithm combination current grid at potential field power direction it is related adjacent to grid to Biomimetic Fish
Pheromones, the probability selection moving direction of calculating transformer minitype bionic fish next step grid；
The probability selection moving direction that ant in step 4, ant colony obtains according to step 3 is moved to next grid, and
Judge whether the current grid falls into trap, taboo list is added in the current grid if not, is otherwise reentered into ant
Starting point restarts；
Whether the mobile current location of step 5, interpretation transformer micro robot fish reaches target position described in step 1
It sets, such as without the position for reaching specified target point, then gos to step 2 up to finding target point, terminate.
Moreover, on the inside transformer surrounding three-dimensional grating map that the step 1 obtains, when the element in transformer occupies
When being discontented with a grid, it can be calculated according to a grid is occupied；
The initialization of the Artificial Potential Field Method includes: gravitational coefficients, repulsion coefficient；
It is described improve ant group algorithm initialization include: the quantity of ant in ant colony, heuristic factor, it is expected heuristic factor,
The number of iterations, pheromones volatility coefficient and taboo list.
Moreover, the step 2 is using grid shared by the minitype bionic fish in Artificial Potential Field Method calculating transformer Raster Data Model
Potential field resultant force Fto(Pf) are as follows:
Wherein, Fat(Pf) it is target point to the gravitation generated at grid shared by minitype bionic fish, Frej(Pf) it is j-th of barrier
Hinder object grid to the repulsion generated at grid shared by minitype bionic fish, j=1,2,3 ... .m indicate the sequence of grid shared by barrier
Column；
Wherein, gravitation Fat(Pf), repulsion Frej(Pf) are as follows:
Wherein, (xg,yg,zg) it is target point PgThree-dimensional coordinate, (x, y, z) is minitype bionic fish position PfThree-dimensional sit
Mark；It is three-dimensional system of coordinate X-axis, Y-axis, the unit vector of Z axis respectively；(xoj,yoj,zoj) it is Obstacle Position Poj
Three-dimensional coordinate；(x, y, z) is minitype bionic fish position PfThree-dimensional coordinate；ρ0For the biggest impact distance of barrier.
Moreover, improved ant group algorithm in the step 3 are as follows: according to the Artificial Potential Field resultant force F obtained in step 2to(Pf),
Referring to the state transition probability formula of ant group algorithm, ant group algorithm is improved, ant selects next node according to formula below:
ηj=5/ (dg-dj)
Wherein,Indicate single ant from i-th of grid motion to the probability of adjacent j-th of grid；φijIndicate people
The angle of work potential field resultant force and the direction grid j；C indicates the neighbouring grid set around grid i；ηjIt is improved inspiration degree.
The advantages of the present invention:
The present invention provides a kind of based on the transformer minitype bionic fish global path planning method for improving ant group algorithm, benefit
Manually potential field method is that ant group algorithm path optimizing of the invention improves " directionality ", keeps transformer minitype bionic fish no longer blind
Mesh scans for, and improves algorithm search speed and global optimizing ability.
2, Grid Method is applied to the three-dimensional modeling of inside transformer complex environment by the present invention, can significantly reduce storage
Data volume, the volumes of searches of the update of data and data；
3, the present invention uses the potential field of grid shared by the minitype bionic fish in Artificial Potential Field Method calculating transformer Raster Data Model
With joint efforts, and the differential seat angle of the direction of motion of calculating transformer minitype bionic fish and potential field resultant force, miniature imitative by referring to transformer
The direction of potential field power can improve " directionality " for ant group algorithm path optimizing of the invention at raw fish corral lattice, keep transformer miniature
Biomimetic Fish no longer blindly scans for
4, the present invention uses in the state transition probability formula of improved ant group algorithm in addition to introducing Artificial Potential Field resultant force Fto
(Pf) outside direction, inspiration degree η j, η j is also improved and is set as target point and current minitype bionic fish distance between grid
Inverse, the effect of this function are to increase object to the attraction of minitype bionic fish when minitype bionic fish is close to object.Into
One step improves " directionality " of the optimizing of ant group algorithm path, and then improves algorithm search speed and global optimizing ability.
Detailed description of the invention
Fig. 1 is a kind of transformer minitype bionic fish global path planning method based on improvement ant group algorithm of the invention
Flow chart；
Fig. 2 is the mobile schematic diagram of the three-dimensional of transformer minitype bionic fish of the invention in inside transformer environment.
Specific embodiment
The embodiment of the present invention is described in further detail below in conjunction with attached drawing:
A kind of transformer minitype bionic fish global path planning method based on improvement ant group algorithm, such as Fig. 1 and Fig. 2 institute
Show, comprising the following steps:
Step 1 establishes inside transformer surrounding three-dimensional grating map, transformer three-dimensional environment cartographic information is carried out initial
Change, the initialization and improvement ant colony of initial position and target position, Artificial Potential Field Method including transformer minitype bionic fish movement
The initialization of algorithm；
On the inside transformer surrounding three-dimensional grating map that the step 1 obtains, it is discontented with when the element in transformer occupies
When one grid, it can be calculated according to a grid is occupied；
The initialization of the Artificial Potential Field Method includes: gravitational coefficients, repulsion coefficient；
It is described improve ant group algorithm initialization include: the quantity of ant in ant colony, heuristic factor, it is expected heuristic factor,
The number of iterations, pheromones volatility coefficient and taboo list；
In the present embodiment, which is subjected to the modeling of 60 × 30 × 10 grids, when the element in transformer occupies not
When a full grid, it can be calculated according to a grid is occupied, grid environmental information is indicated with 0 and 1, and 0 indicates accessible grid,
1 indicates obstacle grid；Setting ant number is M, heuristic factor α, it is expected that heuristic factor is β, the number of iterations N, information
Plain volatility coefficient is ρ, taboo list Bi(grid point that ant i currently passes by) isThe starting point and ending point of ant is set；If
Set the gravitational coefficients K of Artificial Potential Field MethodatWith repulsion coefficient Kre。
Step 2 is closed using the potential field of grid shared by the minitype bionic fish in Artificial Potential Field Method calculating transformer Raster Data Model
Power, and the differential seat angle of the direction of motion of calculating transformer minitype bionic fish and potential field resultant force；
In the present embodiment, the step 2 is using the minitype bionic fish in Artificial Potential Field Method calculating transformer Raster Data Model
The potential field resultant force F of shared gridto(Pf) are as follows:
Wherein, Fat(Pf) it is target point to the gravitation generated at grid shared by minitype bionic fish, Frej(Pf) it is j-th of barrier
Hinder object grid to the repulsion generated at grid shared by minitype bionic fish, j=1,2,3 ... .m indicate the sequence of grid shared by barrier
Column；
Wherein, gravitation Fat(Pf), repulsion Frej(Pf) are as follows:
Wherein, (xg,yg,zg) it is target point PgThree-dimensional coordinate, (x, y, z) is minitype bionic fish position PfThree-dimensional sit
Mark；It is three-dimensional system of coordinate X-axis, Y-axis, the unit vector of Z axis respectively；(xoj,yoj,zoj) it is Obstacle Position Poj
Three-dimensional coordinate；(x, y, z) is minitype bionic fish position PfThree-dimensional coordinate；ρ0It is preparatory for the biggest impact distance of barrier
It sets.
Step 3, using improve ant group algorithm combination current grid at potential field power direction it is related adjacent to grid to Biomimetic Fish
Pheromones, the probability selection moving direction of calculating transformer minitype bionic fish next step grid；
Improved ant group algorithm in the step 3 are as follows: according to the Artificial Potential Field resultant force F obtained in step 2to(Pf), reference
The state transition probability formula of ant group algorithm improves ant group algorithm, and ant selects next node according to formula below:
ηj=5/ (dg-dj)
Wherein,Indicate single ant from i-th of grid motion to the probability of adjacent j-th of grid；φijIndicate people
The angle of work potential field resultant force and the direction grid j；C indicates the neighbouring grid set around grid i；ηjIt is improved inspiration degree,
It is set as the inverse of target point and current minitype bionic fish distance between grid, the effect of this function is when minitype bionic fish leans on
When close-target object, increase object to the attraction of minitype bionic fish.
The probability selection moving direction that ant in step 4, ant colony obtains according to step 3 is moved to next grid, and
Judge whether the current grid falls into trap, taboo list is added in the current grid if not, is otherwise reentered into ant
Starting point restarts；
Whether the mobile current location of step 5, interpretation transformer micro robot fish reaches target position described in step 1
It sets, such as without the position for reaching specified target point, then gos to step 2 up to finding target point, terminate.
As shown in Fig. 2, the internal environment model based on established transformer, micro- mainly including transformer case and winding
Type machine fish can cook up the optimal movement routine of collisionless between starting point and target point.
It is emphasized that embodiment of the present invention be it is illustrative, without being restrictive, therefore the present invention includes
It is not limited to embodiment described in specific embodiment, it is all to be obtained according to the technique and scheme of the present invention by those skilled in the art
Other embodiments, also belong to the scope of protection of the invention.
Claims (4)
1. a kind of based on the transformer minitype bionic fish global path planning method for improving ant group algorithm, it is characterised in that: including
Following steps:
Step 1 establishes inside transformer surrounding three-dimensional grating map, and transformer three-dimensional environment cartographic information is initialized,
The initialization of initial position and target position, Artificial Potential Field Method including transformer minitype bionic fish movement and improvement ant group algorithm
Initialization；
Step 2, the potential field resultant force using grid shared by the minitype bionic fish in Artificial Potential Field Method calculating transformer Raster Data Model, and
The direction of motion of calculating transformer minitype bionic fish and the differential seat angle of potential field resultant force；
Step 3, using improve ant group algorithm combination current grid at potential field power direction and Biomimetic Fish adjacent to the relevant letter of grid
Breath element, the probability selection moving direction of calculating transformer minitype bionic fish next step grid；
The probability selection moving direction that ant in step 4, ant colony obtains according to step 3 is moved to next grid, and judges
Whether the current grid falls into trap, and taboo list is added in the current grid if not, ant is otherwise reentered into starting
Point restarts；
Whether the mobile current location of step 5, interpretation transformer micro robot fish reaches target position described in step 1, such as
The position of specified target point is not reached, then gos to step 2 up to finding target point, terminates.
2. according to claim 1 a kind of based on the transformer minitype bionic fish global path planning side for improving ant group algorithm
Method, it is characterised in that: on the inside transformer surrounding three-dimensional grating map that the step 1 obtains, when the element in transformer accounts for
When with being discontented with a grid, it can be calculated according to a grid is occupied；
The initialization of the Artificial Potential Field Method includes: gravitational coefficients, repulsion coefficient；
The initialization for improving ant group algorithm includes: the quantity of ant in ant colony, heuristic factor, expectation heuristic factor, iteration
Number, pheromones volatility coefficient and taboo list.
3. according to claim 1 a kind of based on the transformer minitype bionic fish global path planning side for improving ant group algorithm
Method, it is characterised in that: the step 2 is using grid shared by the minitype bionic fish in Artificial Potential Field Method calculating transformer Raster Data Model
Potential field resultant force Fto(Pf) are as follows:
Wherein, Fat(Pf) it is target point to the gravitation generated at grid shared by minitype bionic fish, Frej(Pf) it is j-th of barrier grid
Lattice indicate the sequence of grid shared by barrier to the repulsion generated at grid shared by minitype bionic fish, j=1,2,3 ... .m；
Wherein, gravitation Fat(Pf), repulsion Frej(Pf) are as follows:
Wherein, (xg,yg,zg) it is target point PgThree-dimensional coordinate, (x, y, z) is minitype bionic fish position PfThree-dimensional coordinate；It is three-dimensional system of coordinate X-axis, Y-axis, the unit vector of Z axis respectively；(xoj,yoj,zoj) it is Obstacle Position Poj's
Three-dimensional coordinate；(x, y, z) is minitype bionic fish position PfThree-dimensional coordinate；ρ0For the biggest impact distance of barrier.
4. according to claim 1 a kind of based on the transformer minitype bionic fish global path planning side for improving ant group algorithm
Method, it is characterised in that: improved ant group algorithm in the step 3 are as follows: according to the Artificial Potential Field resultant force F obtained in step 2to
(Pf), referring to the state transition probability formula of ant group algorithm, ant group algorithm is improved, ant selects next according to formula below
Node:
ηj=5/ (dg-dj)
Wherein,Indicate single ant from i-th of grid motion to the probability of adjacent j-th of grid；φijIndicate artificial gesture
The angle of occasion power and the direction grid j；C indicates the neighbouring grid set around grid i；ηjIt is improved inspiration degree.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910723996.1A CN110362116A (en) | 2019-08-07 | 2019-08-07 | Based on the transformer minitype bionic fish global path planning method for improving ant group algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910723996.1A CN110362116A (en) | 2019-08-07 | 2019-08-07 | Based on the transformer minitype bionic fish global path planning method for improving ant group algorithm |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110362116A true CN110362116A (en) | 2019-10-22 |
Family
ID=68222116
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910723996.1A Pending CN110362116A (en) | 2019-08-07 | 2019-08-07 | Based on the transformer minitype bionic fish global path planning method for improving ant group algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110362116A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111638722A (en) * | 2020-05-12 | 2020-09-08 | 国网天津市电力公司电力科学研究院 | Miniature bionic fish attitude control method for oil-immersed transformer |
| CN117288209A (en) * | 2023-11-27 | 2023-12-26 | 南昌工程学院 | Transformer sound level measuring method and system |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107917711A (en) * | 2017-11-14 | 2018-04-17 | 重庆邮电大学 | A kind of Robot Path Planning Algorithm based on optimization hybrid ant colony |
| CN108563239A (en) * | 2018-06-29 | 2018-09-21 | 电子科技大学 | A kind of unmanned aerial vehicle flight path planing method based on potential field ant group algorithm |
| CN109282815A (en) * | 2018-09-13 | 2019-01-29 | 天津西青区瑞博生物科技有限公司 | Method for planning path for mobile robot based on ant group algorithm under a kind of dynamic environment |
-
2019
- 2019-08-07 CN CN201910723996.1A patent/CN110362116A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107917711A (en) * | 2017-11-14 | 2018-04-17 | 重庆邮电大学 | A kind of Robot Path Planning Algorithm based on optimization hybrid ant colony |
| CN108563239A (en) * | 2018-06-29 | 2018-09-21 | 电子科技大学 | A kind of unmanned aerial vehicle flight path planing method based on potential field ant group algorithm |
| CN109282815A (en) * | 2018-09-13 | 2019-01-29 | 天津西青区瑞博生物科技有限公司 | Method for planning path for mobile robot based on ant group algorithm under a kind of dynamic environment |
Non-Patent Citations (1)
| Title |
|---|
| 刘力卿: "油浸式变压器微型仿生鱼全局路径规划策略", 《科学技术与工程》 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111638722A (en) * | 2020-05-12 | 2020-09-08 | 国网天津市电力公司电力科学研究院 | Miniature bionic fish attitude control method for oil-immersed transformer |
| CN111638722B (en) * | 2020-05-12 | 2023-04-28 | 国网天津市电力公司电力科学研究院 | Miniature bionic fish attitude control method for oil immersed transformer |
| CN117288209A (en) * | 2023-11-27 | 2023-12-26 | 南昌工程学院 | Transformer sound level measuring method and system |
| CN117288209B (en) * | 2023-11-27 | 2024-01-30 | 南昌工程学院 | Transformer sound level measuring method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109945873A (en) | A kind of mixed path planing method for indoor mobile robot motion control | |
| Liu et al. | Dynamic path planning for mobile robot based on improved genetic algorithm | |
| CN109341707A (en) | Mobile robot three-dimensional map construction method under circumstances not known | |
| CN107943053A (en) | A kind of paths planning method of mobile robot | |
| CN109059924A (en) | Adjoint robot Incremental Route method and system for planning based on A* algorithm | |
| CN110220525A (en) | A kind of paths planning method based on potential field ant group algorithm | |
| CN110375761A (en) | Automatic driving vehicle paths planning method based on enhancing ant colony optimization algorithm | |
| CN105467838B (en) | A kind of synchronous superposition method under stochastic finite collection framework | |
| CN110362116A (en) | Based on the transformer minitype bionic fish global path planning method for improving ant group algorithm | |
| CN110320930A (en) | The reliable transform method of multiple no-manned plane flight pattern based on Voronoi diagram | |
| CN107992040B (en) | Robot path planning method based on combination of map grid and QPSO algorithm | |
| CN102467753A (en) | Method and system for reconstructing time-varying point cloud based on framework registration | |
| CN106792750B (en) | A kind of node deployment method based on guiding particle swarm algorithm | |
| CN106931970A (en) | Robot security's contexture by self air navigation aid in a kind of dynamic environment | |
| CN112666957A (en) | Underwater robot path planning method based on improved ant colony algorithm | |
| CN104548598A (en) | Virtual reality scene path searching method | |
| CN110006434B (en) | Underwater glider path planning method based on ant colony algorithm obstacle avoidance in thermocline sea area | |
| CN103699136A (en) | Intelligent household service robot system and service method based on leapfrogging algorithm | |
| CN110045738A (en) | Robot path planning method based on ant group algorithm and Maklink figure | |
| CN110514567B (en) | Gas source searching method based on information entropy | |
| CN109269518A (en) | A kind of movable fixture confined space path generating method based on intelligent body | |
| CN113110604B (en) | Path dynamic planning method based on artificial potential field | |
| CN107833239A (en) | A kind of searching of optimal matching method for tracking target based on weighted model constraint | |
| CN106211256A (en) | A kind of Unmanned Aerial Vehicle Data collection method based on data critical node | |
| Zhu et al. | A* algorithm of global path planning based on the grid map and V-graph environmental model for the mobile robot |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20191022 |
|
| RJ01 | Rejection of invention patent application after publication |